Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora

ACL 2018

Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora

Jan 28, 2021
|
28 views
|
|
Code
Details
Abstract: Methods for unsupervised hypernym detection may broadly be categorized according to two paradigms: pattern-based and distributional methods. In this paper, we study the performance of both approaches on several hyper-nymy tasks and find that simple pattern-based methods consistently outperform distributional methods on common benchmark datasets. Our results show that pattern-based models provide important contextual constraints which are not yet captured in distributional methods. Authors: Stephen Roller, Douwe Kiela, Maximilian Nickel (Facebook AI Research)

Comments
loading...